Abstract
The paper describes a novel approach to Multi-Engine Machine Translation. We build statistical models of performance of translations and use them to guide us in combining and selecting from outputs from multiple MT engines. We empirically demonstrate that the MEMT system based on the models outperforms any of its component engine.- Anthology ID:
- 2003.mtsummit-papers.36
- Volume:
- Proceedings of Machine Translation Summit IX: Papers
- Month:
- September 23-27
- Year:
- 2003
- Address:
- New Orleans, USA
- Venue:
- MTSummit
- SIG:
- Publisher:
- Note:
- Pages:
- Language:
- URL:
- https://aclanthology.org/2003.mtsummit-papers.36
- DOI:
- Cite (ACL):
- Tadashi Nomoto. 2003. Predictive models of performance in multi-engine machine translation. In Proceedings of Machine Translation Summit IX: Papers, New Orleans, USA.
- Cite (Informal):
- Predictive models of performance in multi-engine machine translation (Nomoto, MTSummit 2003)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2003.mtsummit-papers.36.pdf